Introduction -

Choosing between Universities is something we all go through at some or the other point in our lives. Why do you select a certain University over others? Is it because it is reputed? Is it the rank of the University? Is it the Quality of education and faculty? Or just because your friend is joining that same Institution? I hope its not that last option that you prioritize first, haha!

Having joined Monash University in Feb 2020, I’m always asked questions about my experience about the same. This is something I myself did before joining because it’s a major decision in one’s life and we need to know about our options thoroughly and transparently from someone who is actually walking the path we intend to take. I thought this Data Story would help future students and also help me analyze my own decisions in life. Why exactly did I choose Monash? Here’s my story at Monash and I would like to back it up with facts since I specialize in Business Analytics!

University ranking is a measurable outcome of multiple factors that are considered to evaluate the standard of education, faculty, resources, and infrastructure. Every year, Universities are ranked by different organizations around the world like CWUR, Times Higher Education, Quacquarelli Symmonds (QS) and many others. We are using a dataset that contains rankings of the world universities as maintained by QS.

Quacquarelli Symmonds (QS) is a British think-tank company specializing in the analysis of higher education institutions throughout the world. It uses 6 factors for their ranking framework wiz. Academic Reputation, Employer Reputation, Faculty to Student Ratio, Number of Citations per Faculty, International Faculty, and International Students. Another feature included in this data was Classification (which is not used for ranking) which included the institution’s size, subject range, research intensity, age, and status.

This Data Exploration Project is an effort to answer some questions around the analysis of higher education institutions such as the following –

  1. What factors other than rank is more desirable when deciding the quality of a University? In other words, how do Universities compare in terms of the 6 factors in QS factor classification?

  2. Which Universities top in each of the specific factors?

  3. Is there a correlation between different classification factors like Country, Age of the University, Reputation of the University, Size and International Student Numbers?

Data Description -

Data Checking -

A glimpse of the Raw Data is as follows –

#reading the data
Uni2020 <- read.csv(here::here("Data/Clean/2020-QS-World-University-Rankings.csv"))
#datatype tranformation
TopUni2020 <- Uni2020 %>% select(-Rank.in.2019) %>% mutate(
                   SIZE = as.factor(SIZE),
                   FOCUS = as.factor(FOCUS),
                   RESEARCH.INTENSITY = as.factor(RESEARCH.INTENSITY),
                   AGE = as.factor(AGE),
                   STATUS = as.factor(STATUS),
                   AcademicSCORE = as.double(AcademicSCORE),
                   EmpSCORE = as.double(EmpSCORE),
                   RatioSCORE = as.double(RatioSCORE),
                   CiteSCORE = as.double(CiteSCORE),
                   IntFacSCORE = as.double(IntFacSCORE),
                   IntStuSCORE = as.double(IntStuSCORE),
                   AcademicRANK = as.integer(AcademicRANK),
                   EmpRANK = as.integer(EmpRANK),
                   RatioRANK = as.integer(RatioRANK),
                   CiteRANK = as.integer(CiteRANK),
                   IntFacRANK = as.integer(IntFacRANK),
                   IntStuRANK = as.integer(IntStuRANK),
                   Overall.Score = as.double(Overall.Score))
Visualizing the transformed data-types of the columns

Visualizing the transformed data-types of the columns

The list of Universities in the QS dataset considered with Rank and Name of University is as follows -

My Experience at Monash -

Having learned the skill of analyzing raw data and turning them into useful insights for decision making, this was one of the best topics to choose. This serves as a helpful guide to students and also help me showcase my skills, both at once! This felt like a creative mini data story that I wanted to create not just to showcase my skills, but also with an intention to help people!

The important classification factors are as follows -

Data Exploration -

1. What factors other than rank is more desirable when deciding the quality of a University? How do Universities compare in terms of the 6 factors in QS factor classification?

Correlation between Rank of the University and 6 factors

Correlation between Rank of the University and 6 factors

  • From the figure above, Academic Reputation and Employer Reputation Scores have a strong correlation as the Rank value increases from 1-100. This means that better the University rank, better is the Academic Quality and Employers seek graduates from top universities in general.

  • Faculty to Student Ratio and Citations per Faculty are similar after the 35th Rank and shows lesser correlation.

  • International Faculty and Student Scores are not correlated with rank and show bimodal distribution with the increase in rank value.

  • Thus, we can say that Academic Reputation and Employer Reputation are the factors other than rank that decides the quality of an institution in general. The following table verifies the correlation of factor with Rank.

Factor CorrelationWithRank
Rank.in.2020 1.0000000
AcademicRANK 0.7776026
EmpRANK 0.6018111
RatioRANK 0.3535604
CiteRANK 0.3583584
IntFacRANK 0.2985079

2. Which Universities top in each of the specific factors?

  • We consider the Universities that have a Score of 100/100 in each factor. These are interactive plots that give the Rank, Name, and Overall score of the particular University when hovered over.
  • The figure shows the Universities that are best at Academic Reputation in the QS World Rankings. We can observe that University of Tokyo, UCB, and UCLA which are not in the top 10 ranks have the best Academic Reputation. Harvard, MIT, Stanford, Cambridge, and Oxford which are among the top universities make it into this list which was expected.
  • The figure shows the Universities that are best at Employer Reputation in the QS World Rankings. We can observe that only five universities have a score of 100 in this factor. Harvard, MIT, Stanford, Cambridge, and Oxford, all of which are in the top ten have made it into this list. This shows that employers mostly seek students from the topmost universities.
  • The figure shows the Universities that are best at Faculty to Student Ratio in the QS World Rankings. We can see that Universities ranked at 31st, 53rd, and 81st have made it into this list. This means to say that the universities in this list have a greater number of faculty in comparison to the number of students in that university. We can observe that some of the universities ranked lower also have ample number of faculty per student.
  • The figure shows the Universities that are best at Citations per Faculty in the QS World Rankings. We can observe that only 3 universities in the QS rankings have a score of 100 in this factor. Caltech, Georgia Tech, and Princeton universities have the most citations per faculty. This means to say that the faculty in these universities have the greatest number of research papers and citable work cited under their names.
  • The figure shows the Universities that are best in the number of International Faculty in the QS World Rankings. There is a long list of universities that have a score of 100 under this factor. This goes to show that these universities are multicultural and have faculty from different countries from all around the globe.
  • The figure shows the Universities that are best in the number of International Students in the QS World Rankings. Only 6 universities in the data have made it to this list with a score of 100 in the factor. This goes out to show that these universities are diverse and multicultural in their student population and accept students from a broad array of backgrounds and cultures.

  • The top universities in each factor are listed above and this answers our question as to which is best in what factor. We can make a choice based on the kind of environment we’re looking for in a university and the factor that matters most to us.

  • These plots verify our previous conclusion that Academic Reputation and Employer Reputation have a strong correlation with the rank of the University compared to the other factors with Overall Score ranging above 85 at least!

3. Is there a correlation between different classification factors like Country, Age of the University, Reputation of the University, Size and International Student Numbers?

  • Distribution of Top 100 Universities in each country.
Country-wise Frequency Distribution of the Top 100 Universities in QS World Rankings.

Country-wise Frequency Distribution of the Top 100 Universities in QS World Rankings.

  • It is evident from the above figure that US/UK have the greatest number of universities in the Top 100 rankings worldwide with 29 and 18 universities respectively. Australia has the third highest number of Universities in the Top 100 with 7 and the rest of the countries in the list has 6 or lesser universities in the Top 100. This plot was built using Tableau.

  • Is there a relationship between age of the university and its employer reputation?

Age versus Employer Reputation of Universities

Age versus Employer Reputation of Universities

     5 = Greater than 100 years old (Historic Universities)
     4 = 50-100 years old (Mature Universities)
     3 = 25-50 years old (Established Universities)
     1 and 2 = Less than 25 years old (Young Universities)
  • We can see that generally the historic and mature universities have better employer reputation. A higher SCORE and lower RANK is the desirable reading which is mostly found in the older universities. Thus, employer reputation generally increases with the age of the university.

  • Is there a relationship between institution size and number of international students?

Size versus International Student Scores and Rank

Size versus International Student Scores and Rank

                XL = Greater than 30,000
                 L = Greater than 12,000
                 M = Greater than  5,000
                 S = Lesser  than  5,000
  • We can observe that the Small (S) and Medium (M) sized universities have the greatest diversity among students with a greater number of international students compared to Large (L) and Extra Large (XL) sized universities. They have a desirable reading of higher SCORE and lower RANK values. Thus, a higher number of students count does not mean that there will be more diversity in the student population.

Conclusion -

From the Data Exploration and Visualization conducted in the previous section, we can conclude that –

Hope this gives a comprehensive overview to all the young and aspiring students who are looking forward to pursue higher education for their career! Share this with someone you think will benefit from!

References -